2 results found Sort:

sail-sg
oat sail-sg
8
127
apache-2.0
5
🌾 OAT: A research-friendly framework for LLM online alignment, including preference learning, reinforcement learning, etc.
dpo llm rlhf alignment online-rl reasoning llm-aligment distributed-rl dueling-bandits llm-exploration online-alignment thompson-sampling distributed-training
Created 2024-10-15
26 commits to main branch, last one 2 days ago
Zanette-Labs
SpeculativeRejection Zanette-Labs
3
38
unknown
1
[NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection
best-of-n acceleration llm-aligment inference-scaling
Created 2024-10-17
5 commits to main branch, last one 3 months ago